Optimal Transport-inspired Deep Learning Framework for Slow-Decaying Problems: Exploiting Sinkhorn Loss and Wasserstein Kernel

arXiv2308.13840MaRDI QIDQ6448733FDOQ6448733

Authors: Moaad Khamlich, Federico Pichi, Gianluigi Rozza 

Publication date: 26 August 2023

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Convex programming (90C25) Interpolation in approximation theory (41A05) Finite element, Rayleigh-Ritz and Galerkin methods for boundary value problems involving PDEs (65N30) Numerical approximation and computational geometry (primarily algorithms) (65D99) Approximation by arbitrary nonlinear expressions; widths and entropy (41A46)

This page was built for publication: Optimal Transport-inspired Deep Learning Framework for Slow-Decaying Problems: Exploiting Sinkhorn Loss and Wasserstein Kernel

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6448733)